Spaces:
Sleeping
Sleeping
File size: 7,035 Bytes
b7f710c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 |
from typing import Tuple
import numpy as np
import torch
from PIL import Image
from torch.autograd import Variable
import sys
import os
sys.path.insert(0, os.path.dirname(__file__))
from mtcnn_pytorch.src.get_nets import PNet, RNet, ONet
from mtcnn_pytorch.src.box_utils import nms, calibrate_box, get_image_boxes, convert_to_square
from mtcnn_pytorch.src.first_stage import run_first_stage
from mtcnn_pytorch.src.align_trans import get_reference_facial_points, warp_and_crop_face
class MTCNN():
def __init__(self, device: str = 'cuda:0', crop_size: Tuple[int, int] = (112, 112)):
assert device in ['cuda:0', 'cpu']
self.device = torch.device(device)
assert crop_size in [(112, 112), (96, 112)]
self.crop_size = crop_size
# change working dir to this file location to load npz files. Then switch back
cwd = os.getcwd()
os.chdir(os.path.dirname(__file__))
self.pnet = PNet().to(self.device)
self.rnet = RNet().to(self.device)
self.onet = ONet().to(self.device)
self.pnet.eval()
self.rnet.eval()
self.onet.eval()
self.refrence = get_reference_facial_points(default_square=crop_size[0] == crop_size[1])
self.min_face_size = 20
self.thresholds = [0.6,0.7,0.9]
self.nms_thresholds = [0.7, 0.7, 0.7]
self.factor = 0.85
os.chdir(cwd)
def align(self, img):
_, landmarks = self.detect_faces(img, self.min_face_size, self.thresholds, self.nms_thresholds, self.factor)
facial5points = [[landmarks[0][j], landmarks[0][j + 5]] for j in range(5)]
warped_face = warp_and_crop_face(np.array(img), facial5points, self.refrence, crop_size=self.crop_size)
return Image.fromarray(warped_face)
def align_multi(self, img, limit=None):
boxes, landmarks = self.detect_faces(img, self.min_face_size, self.thresholds, self.nms_thresholds, self.factor)
if limit:
boxes = boxes[:limit]
landmarks = landmarks[:limit]
faces = []
for landmark in landmarks:
facial5points = [[landmark[j], landmark[j + 5]] for j in range(5)]
warped_face = warp_and_crop_face(np.array(img), facial5points, self.refrence, crop_size=self.crop_size)
faces.append(Image.fromarray(warped_face))
return boxes, faces
def detect_faces(self, image, min_face_size, thresholds, nms_thresholds, factor):
"""
Arguments:
image: an instance of PIL.Image.
min_face_size: a float number.
thresholds: a list of length 3.
nms_thresholds: a list of length 3.
Returns:
two float numpy arrays of shapes [n_boxes, 4] and [n_boxes, 10],
bounding boxes and facial landmarks.
"""
# BUILD AN IMAGE PYRAMID
width, height = image.size
min_length = min(height, width)
min_detection_size = 12
# factor = 0.707 # sqrt(0.5)
# scales for scaling the image
scales = []
# scales the image so that
# minimum size that we can detect equals to
# minimum face size that we want to detect
m = min_detection_size / min_face_size
min_length *= m
factor_count = 0
while min_length > min_detection_size:
scales.append(m * factor**factor_count)
min_length *= factor
factor_count += 1
# STAGE 1
# it will be returned
bounding_boxes = []
with torch.no_grad():
# run P-Net on different scales
for s in scales:
boxes = run_first_stage(image, self.pnet, scale=s, threshold=thresholds[0])
bounding_boxes.append(boxes)
# collect boxes (and offsets, and scores) from different scales
bounding_boxes = [i for i in bounding_boxes if i is not None]
if len(bounding_boxes) == 0:
return [], []
bounding_boxes = np.vstack(bounding_boxes)
keep = nms(bounding_boxes[:, 0:5], nms_thresholds[0])
bounding_boxes = bounding_boxes[keep]
# use offsets predicted by pnet to transform bounding boxes
bounding_boxes = calibrate_box(bounding_boxes[:, 0:5], bounding_boxes[:, 5:])
# shape [n_boxes, 5]
bounding_boxes = convert_to_square(bounding_boxes)
bounding_boxes[:, 0:4] = np.round(bounding_boxes[:, 0:4])
# STAGE 2
img_boxes = get_image_boxes(bounding_boxes, image, size=24)
img_boxes = torch.FloatTensor(img_boxes).to(self.device)
output = self.rnet(img_boxes)
offsets = output[0].cpu().data.numpy() # shape [n_boxes, 4]
probs = output[1].cpu().data.numpy() # shape [n_boxes, 2]
keep = np.where(probs[:, 1] > thresholds[1])[0]
bounding_boxes = bounding_boxes[keep]
bounding_boxes[:, 4] = probs[keep, 1].reshape((-1, ))
offsets = offsets[keep]
keep = nms(bounding_boxes, nms_thresholds[1])
bounding_boxes = bounding_boxes[keep]
bounding_boxes = calibrate_box(bounding_boxes, offsets[keep])
bounding_boxes = convert_to_square(bounding_boxes)
bounding_boxes[:, 0:4] = np.round(bounding_boxes[:, 0:4])
# STAGE 3
img_boxes = get_image_boxes(bounding_boxes, image, size=48)
if len(img_boxes) == 0:
return [], []
img_boxes = torch.FloatTensor(img_boxes).to(self.device)
output = self.onet(img_boxes)
landmarks = output[0].cpu().data.numpy() # shape [n_boxes, 10]
offsets = output[1].cpu().data.numpy() # shape [n_boxes, 4]
probs = output[2].cpu().data.numpy() # shape [n_boxes, 2]
keep = np.where(probs[:, 1] > thresholds[2])[0]
bounding_boxes = bounding_boxes[keep]
bounding_boxes[:, 4] = probs[keep, 1].reshape((-1, ))
offsets = offsets[keep]
landmarks = landmarks[keep]
# compute landmark points
width = bounding_boxes[:, 2] - bounding_boxes[:, 0] + 1.0
height = bounding_boxes[:, 3] - bounding_boxes[:, 1] + 1.0
xmin, ymin = bounding_boxes[:, 0], bounding_boxes[:, 1]
landmarks[:, 0:5] = np.expand_dims(xmin, 1) + np.expand_dims(width, 1) * landmarks[:, 0:5]
landmarks[:, 5:10] = np.expand_dims(ymin, 1) + np.expand_dims(height, 1) * landmarks[:, 5:10]
bounding_boxes = calibrate_box(bounding_boxes, offsets)
keep = nms(bounding_boxes, nms_thresholds[2], mode='min')
bounding_boxes = bounding_boxes[keep]
landmarks = landmarks[keep]
return bounding_boxes, landmarks
|